• Journal of Information Processing Systems
• /
• v.18 no.3
• /
• pp.389-401
• /
• 2022

The business of Internet of Vehicles (IoV) is growing rapidly, and the large amount of data exchange has caused problems of large mobile network communication delay and large energy loss. A strategy for resource allocation of IoV communication based on mobile edge computing (MEC) is thus proposed. First, a model of the cloud-side collaborative cache and resource allocation system for the IoV is designed. Vehicles can offload tasks to MEC servers or neighboring vehicles for communication. Then, the communication model and the calculation model of IoV system are comprehensively analyzed. The optimization objective of minimizing delay and energy consumption is constructed. Finally, the on-board computing task is coded, and the optimization problem is transformed into a knapsack problem. The optimal resource allocation strategy is obtained through genetic algorithm. The simulation results based on the MATLAB platform show that: The proposed strategy offloads tasks to the MEC server or neighboring vehicles, making full use of system resources. In different situations, the energy consumption does not exceed 300 J and 180 J, with an average delay of 210 ms, effectively reducing system overhead and improving response speed.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.442-445
• /
• 2023

최근 딥러닝 및 로봇기술의 발전으로 인해 대량의 데이터를 빠르게 수집하고 처리하는 연구 분야들로 확대되었다. 이와 관련된 한 가지 분야로써 다중 로봇을 이용한 분산학습 연구가 있으며, 이는 단일 에이전트를 이용할 때보다 대량의 데이터를 빠르게 수집 및 처리하는데 용이하다. 본 연구에서는 기존 Distributed Neural Network Optimization (DiNNO) 알고리즘에서 제안한 정적 분산 학습방법과 달리 단계적 분산학습 방법을 새롭게 제안하였으며, 모델 성능을 향상시키기 위해 원시 변수를 근사하는 단계수를 상수로 고정하는 기존의 방식에서 통신회차가 늘어남에 따라 점진적으로 근사 횟수를 높이는 방법을 고안하여 새로운 알고리즘을 제안하였다. 기존 알고리즘과 제안된 알고리즘의 정성 및 정량적 성능 평가를 수행하기 MNIST 분류와 2 차원 평면도 지도화 실험을 수행하였으며, 그 결과 제안된 알고리즘이 기존 DiNNO 알고리즘보다 동일한 통신회차에서 높은 정확도를 보임과 함께 전역 최적점으로 빠르게 수렴하는 것을 입증하였다.

• Nuclear Engineering and Technology
• /
• v.55 no.1
• /
• pp.339-352
• /
• 2023

Prediction of the time-related traits of pebble flow inside pebble-bed HTGRs is of great significance for reactor operation and design. In this work, an image-driven approach with the aid of a convolutional neural network (CNN) is proposed to predict the remaining time of initially loaded pebbles and the time interval of paired flow images of the pebble bed. Two types of strategies are put forward: one is adding FC layers to the classic classification CNN models and using regression training, and the other is CNN-based deep expectation (DEX) by regarding the time prediction as a deep classification task followed by softmax expected value refinements. The current dataset is obtained from the discrete element method (DEM) simulations. Results show that the CNN-aided models generally make satisfactory predictions on the remaining time with the determination coefficient larger than 0.99. Among these models, the VGG19+DEX performs the best and its CumScore (proportion of test set with prediction error within 0.5s) can reach 0.939. Besides, the remaining time of additional test sets and new cases can also be well predicted, indicating good generalization ability of the model. In the task of predicting the time interval of image pairs, the VGG19+DEX model has also generated satisfactory results. Particularly, the trained model, with promising generalization ability, has demonstrated great potential in accurately and instantaneously predicting the traits of interest, without the need for additional computational intensive DEM simulations. Nevertheless, the issues of data diversity and model optimization need to be improved to achieve the full potential of the CNN-aided prediction tool.

• International Journal of Fluid Machinery and Systems
• /
• v.8 no.1
• /
• pp.46-54
• /
• 2015

Thrust-ring-pump is a kind of extreme-low specific speed centrifugal pump with special structure as numerous restrictions from thrust bearing and operation conditions of hydro-generator units. Because the oil circulatory and cooling system with thrust-ring-pump has a lot of advantages in maintenance and compactness in structure, it has widely been used in large and medium-sized hydro-generator units. Since the diameter and the speed of the thrust ring is limited by the generator set, the matching relationship between the flow passage inside the thrust ring (equivalent to impeller) and oil bath (equivalent to volute) has great influence on hydrodynamic performance of thrust-ring-pump. On another hand, the head and flow rate are varying with the operation conditions of hydro-generator units and the oil circulatory and cooling system. As so far, the empirical calculation method is employed during the actual engineering design, in order to guarantee the operating performance of the oil circulatory and cooling system with thrust-ring-pump at different conditions, a collaborative hydrodynamic design and optimization is purposed in this paper. Firstly, the head and flow rate at different conditions are decided by 1D flow numerical simulation of the oil circulatory and cooling system. Secondly, the flow passages of thrust-ring-pump are empirically designed under the restrictions of diameter and the speed of the thrust ring according to the head and flow rate from the simulation. Thirdly, the flow passage geometry matching optimization between thrust ring and oil bath is implemented by means of 3D flow simulation and performance prediction. Then, the pumps and the oil circulatory and cooling system are collaborative hydrodynamic optimized with predicted head-flow rate curve and the efficiency-flow rate curve of thrust-ring-pump. The presented methodology has been adopted by DFEM in design process of thrust-ring-pump and it shown can effectively improve the performance of whole system.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.11
• /
• pp.3030-3049
• /
• 2023

With the development and wide application of hybrid network computing modes like cloud computing, edge computing and fog computing, the customer service requests and the collaborative optimization of various computing resources face huge challenges. Considering the characteristics of network environment resources, the optimized deployment of service resources is a feasible solution. So, in this paper, the optimal goals for deploying service resources are customer experience and service cost. The focus is on the system impact of deploying services on load, fault tolerance, service cost, and quality of service (QoS). Therefore, the alternate node filtering algorithm (ANF) and the adjustment factor of cost matrix are proposed in this paper to enhance the system service performance without changing the minimum total service cost, and corresponding theoretical proof has been provided. In addition, for improving the fault tolerance of system, the alternate node preference factor and algorithm (ANP) are presented, which can effectively reduce the probability of data copy loss, based on which an improved cost-efficient replica deployment strategy named ICERD is given. Finally, by simulating the random occurrence of cloud node failures in the experiments and comparing the ICERD strategy with representative strategies, it has been validated that the ICERD strategy proposed in this paper not only effectively reduces customer access latency, meets customers' QoS requests, and improves system service quality, but also maintains the load balancing of the entire system, reduces service cost, enhances system fault tolerance, which further confirm the effectiveness and reliability of the ICERD strategy.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.1
• /
• pp.211-232
• /
• 2024

In this paper, we consider the resource allocation and offloading decisions of device-to-device (D2D) cooperative UAV-assisted mobile edge computing (MEC) system, where the device with task request is served by unmanned aerial vehicle (UAV) equipped with MEC server and D2D device with idle resources. On the one hand, to ensure the fairness of time-delay sensitive devices, when UAV computing resources are relatively sufficient, an optimization model is established to minimize the maximum delay of device computing tasks. The original non-convex objective problem is decomposed into two subproblems, and the suboptimal solution of the optimization problem is obtained by alternate iteration of two subproblems. On the other hand, when the device only needs to complete the task within a tolerable delay, we consider the offloading priorities of task to minimize UAV computing resources. Then we build the model of joint offloading decision and power allocation optimization. Through theoretical analysis based on KKT conditions, we elicit the relationship between the amount of computing task data and the optimal resource allocation. The simulation results show that the D2D cooperation scheme proposed in this paper is effective in reducing the completion delay of computing tasks and saving UAV computing resources.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.6 no.3
• /
• pp.19-29
• /
• 2010

A marketing model is changed from a customer acquisition to customer retention and it is being moved to a way that enhances the quality of customer interaction to add value to our customers. Such personalization is emerging from this background. The Web site is accelerate the adoption of a personalization, and in contrast to the rapid growth of data, quantitative analytical experience is required. For the automated analysis of large amounts of data and the results must be passed in real time of personalization has been interested in technical problems. A recommendation algorithm is an algorithm for the implementation of personalization, which predict whether the customer preferences and purchasing using the database with new customers interested or likely to purchase. As recommended number of users increases, the algorithm increases recommendation time is the problem. In this paper, to solve this problem, a recommendation system based on clustering and dimensionality reduction is proposed. First, clusters customers with such an orientation, then shrink the dimensions of the relationship between customers to low dimensional space. Because finding neighbors for recommendations is performed at low dimensional space, the computation time is greatly reduced.

• Journal of Information Processing Systems
• /
• v.17 no.5
• /
• pp.905-917
• /
• 2021

In recent years, edge computing technology consists of several Internet of Things (IoT) devices with embedded sensors that have improved significantly for monitoring, detection, and management in an environment where big data is commercialized. The main focus of edge computing is data optimization or task offloading due to data and task-intensive application development. However, existing offloading approaches do not consider correlations and associations between data and tasks involving edge computing. The extent of collaborative offloading segmented without considering the interaction between data and task can lead to data loss and delays when moving from edge to edge. This article proposes a range segmentation of dynamic offloading (RSDO) algorithm that isolates the offload range and collaborative edge node around the edge node function to address the offloading issue.The RSDO algorithm groups highly correlated data and tasks according to the cause of the overload and dynamically distributes offloading ranges according to the state of cooperating nodes. The segmentation improves the overall performance of edge nodes, balances edge computing, and solves data loss and average latency.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.2
• /
• pp.383-403
• /
• 2021

With the development of mobile edge computing (MEC), some late-model application technologies, such as self-driving, augmented reality (AR) and traffic perception, emerge as the times require. Nevertheless, the high-latency and low-reliability of the traditional cloud computing solutions are difficult to meet the requirement of growing smart cars (SCs) with computing-intensive applications. Hence, this paper studies an efficient offloading decision and resource allocation scheme in collaborative vehicular edge computing networks with multiple SCs and multiple MEC servers to reduce latency. To solve this problem with effect, we propose a context-aware offloading strategy based on differential evolution algorithm (DE) by considering vehicle mobility, roadside units (RSUs) coverage, vehicle priority. On this basis, an autoregressive integrated moving average (ARIMA) model is employed to predict idle computing resources according to the base station traffic in different periods. Simulation results demonstrate that the practical performance of the context-aware vehicular task offloading (CAVTO) optimization scheme could reduce the system delay significantly.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.42 no.4
• /
• pp.116-125
• /
• 2019

The Dynamic Vehicle Routing Problem (DVRP) involves a combinatorial optimization problem where new customer demands become known over time, and old routes must be reconfigured to generate new routes while executing the current solution. We consider the high level of dynamism problem. An application of highly dynamic DVRP is the ambulance service where a patient contacts the service center, followed by an evaluation of case severity, and a visit by a practitioner/ ambulance is scheduled accordingly. This paper considers a variant of the DVRP and proposes a decentralized algorithm in which collaborators (Depot and Vehicle), both have only partial information about the entire system. The DVRP is modeled as a periodic re optimization of VRP using the proposed decentralized algorithm where collaborators exchange local information to achieve the best global objective for the current state of the system. We assume the existence of a dispatcher e.g., headquarter of the company who can communicate to vehicles in order to gather information and assigns the new visits to them. The effectiveness of the proposed decentralized coordination algorithm is further evaluated using benchmark data given in literature. The results show that the proposed method performed better than the compared algorithms which utilize the centralized coordination in 12 out of 21 benchmark problems.